A novel Enhanced Collaborative Autoencoder with knowledge distillation for top-N recommender systems
In most recommender systems, the data of user feedbacks are usually represented with a set of discrete values, which are difficult to exactly describe users’ interests. This problem makes it not easy to exactly model users’ latent preferences for recommendation. Intuitively, a basic idea for this is...
Uloženo v:
| Vydáno v: | Neurocomputing (Amsterdam) Ročník 332; s. 137 - 148 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
07.03.2019
|
| Témata: | |
| ISSN: | 0925-2312, 1872-8286 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | In most recommender systems, the data of user feedbacks are usually represented with a set of discrete values, which are difficult to exactly describe users’ interests. This problem makes it not easy to exactly model users’ latent preferences for recommendation. Intuitively, a basic idea for this issue is to predict continuous values through a trained model to reveal users’ essential feedbacks, and then make use of the generated data to retrain another model to learn users’ preferences. However, since these continuous data are generated by an imperfect model which are trained by discrete data, there exists a lot of noise among the generated data. This problem may have a severe adverse impact on the performance. Towards this problem, we propose a novel Enhanced Collaborative Autoencoder (ECAE) to learn robust information from generated soft data with the technique of knowledge distillation. First, we propose a tightly coupled structure to incorporate the generation and retraining stages into a unified framework. So that the generated data can be fine tuned to reduce the noise by propagating training errors of retraining network. Second, for that each unit of the generated data contains different level of noise, we propose a novel distillation layer to balance the influence of noise and knowledge. Finally, we propose to take both predict results of generation and retraining network into account to make final recommendations for each user. The experimental results on four public datasets for top-N recommendation show that the ECAE model performs better than several state-of-the-art algorithms on metrics of MAP and NDCG. |
|---|---|
| AbstractList | In most recommender systems, the data of user feedbacks are usually represented with a set of discrete values, which are difficult to exactly describe users’ interests. This problem makes it not easy to exactly model users’ latent preferences for recommendation. Intuitively, a basic idea for this issue is to predict continuous values through a trained model to reveal users’ essential feedbacks, and then make use of the generated data to retrain another model to learn users’ preferences. However, since these continuous data are generated by an imperfect model which are trained by discrete data, there exists a lot of noise among the generated data. This problem may have a severe adverse impact on the performance. Towards this problem, we propose a novel Enhanced Collaborative Autoencoder (ECAE) to learn robust information from generated soft data with the technique of knowledge distillation. First, we propose a tightly coupled structure to incorporate the generation and retraining stages into a unified framework. So that the generated data can be fine tuned to reduce the noise by propagating training errors of retraining network. Second, for that each unit of the generated data contains different level of noise, we propose a novel distillation layer to balance the influence of noise and knowledge. Finally, we propose to take both predict results of generation and retraining network into account to make final recommendations for each user. The experimental results on four public datasets for top-N recommendation show that the ECAE model performs better than several state-of-the-art algorithms on metrics of MAP and NDCG. |
| Author | Pan, Yiteng He, Fazhi Yu, Haiping |
| Author_xml | – sequence: 1 givenname: Yiteng surname: Pan fullname: Pan, Yiteng – sequence: 2 givenname: Fazhi orcidid: 0000-0001-9167-1683 surname: He fullname: He, Fazhi email: fzhe@whu.edu.cn – sequence: 3 givenname: Haiping orcidid: 0000-0002-8900-8054 surname: Yu fullname: Yu, Haiping |
| BookMark | eNqFkL1OwzAUhS1UJNrCGzD4BRL8kzgJA1JVlR-pggVmy3FuqEtiV7Zp1bcnoUwMMN3lfEfnfjM0sc4CQteUpJRQcbNNLXxq16eM0DKlLCUsP0NTWhYsKVkpJmhKKpYnjFN2gWYhbAmhBWXVFDULbN0eOryyG2U1NHjpuk7Vzqto9oAXn9GB1a4Bjw8mbvCHdYcOmnfAjQnRDNlonMWt8zi6XfKMPQxLerAjEY4hQh8u0XmrugBXP3eO3u5Xr8vHZP3y8LRcrBPNiYhJqRuAss4ypSjLayZUVlcNK7nOFWlJLQQvBM0Eb4uKt4yzNq81B0W0ylvFFJ-j21Ov9i4ED63UJn7vi16ZTlIiR19yK0--5OhLUiYHXwOc_YJ33vTKH__D7k4YDI_tDXgZtIHRpBlMRNk483fBFxT3jAg |
| CitedBy_id | crossref_primary_10_1016_j_asoc_2020_106335 crossref_primary_10_1016_j_chaos_2022_112204 crossref_primary_10_1108_IJICC_11_2021_0257 crossref_primary_10_1007_s12293_021_00328_7 crossref_primary_10_1016_j_eswa_2021_115306 crossref_primary_10_1007_s11042_022_12232_4 crossref_primary_10_3233_ICA_190723 crossref_primary_10_1016_j_aei_2019_100963 crossref_primary_10_1007_s10489_019_01542_0 crossref_primary_10_1016_j_engappai_2024_108792 crossref_primary_10_1109_ACCESS_2019_2940603 crossref_primary_10_1007_s11042_022_13411_z crossref_primary_10_1007_s11257_024_09418_w crossref_primary_10_1007_s11704_019_8123_3 crossref_primary_10_1007_s11042_022_12513_y crossref_primary_10_2196_23086 crossref_primary_10_1007_s11042_022_13281_5 crossref_primary_10_1016_j_engappai_2025_111914 crossref_primary_10_1007_s11042_019_08070_6 crossref_primary_10_3390_math11030761 crossref_primary_10_1007_s11042_019_08399_y crossref_primary_10_1007_s41095_020_0185_5 crossref_primary_10_1016_j_aei_2019_02_003 crossref_primary_10_1016_j_ins_2019_10_072 crossref_primary_10_1007_s40815_021_01177_9 crossref_primary_10_1109_TCE_2023_3325138 crossref_primary_10_1007_s12652_020_02388_y crossref_primary_10_1016_j_neucom_2022_04_082 crossref_primary_10_1371_journal_pone_0255948 crossref_primary_10_3390_sym12101636 crossref_primary_10_3233_IDA_194641 crossref_primary_10_1007_s00371_019_01774_8 crossref_primary_10_1109_TCSVT_2022_3146305 crossref_primary_10_1016_j_eswa_2021_115132 crossref_primary_10_1016_j_measurement_2019_06_029 crossref_primary_10_1007_s10489_021_02872_8 crossref_primary_10_1007_s10489_022_03758_z crossref_primary_10_1016_j_neucom_2021_01_040 crossref_primary_10_1007_s11766_019_3714_1 crossref_primary_10_1007_s10115_024_02204_5 crossref_primary_10_1007_s00371_021_02184_5 crossref_primary_10_1007_s10489_022_04423_1 crossref_primary_10_1109_ACCESS_2021_3133628 crossref_primary_10_1007_s10586_025_05258_4 crossref_primary_10_1016_j_jpdc_2019_05_005 crossref_primary_10_1007_s11042_019_08597_8 crossref_primary_10_1016_j_knosys_2020_106372 crossref_primary_10_1080_03081079_2023_2200248 crossref_primary_10_1007_s11042_019_08493_1 crossref_primary_10_1016_j_dt_2021_04_014 crossref_primary_10_1016_j_future_2019_05_021 crossref_primary_10_1109_ACCESS_2025_3573181 crossref_primary_10_1002_cpe_7241 crossref_primary_10_1016_j_neucom_2024_128718 crossref_primary_10_1109_ACCESS_2021_3057091 crossref_primary_10_1109_TAI_2021_3116551 crossref_primary_10_1007_s11042_023_14704_7 crossref_primary_10_1007_s11042_021_10897_x crossref_primary_10_1007_s11042_021_10890_4 crossref_primary_10_1007_s10489_022_03170_7 crossref_primary_10_1007_s13042_023_01828_3 crossref_primary_10_1177_1063293X21998083 crossref_primary_10_1007_s11042_023_14490_2 crossref_primary_10_1007_s11280_020_00793_z crossref_primary_10_1007_s11704_019_8184_3 crossref_primary_10_1109_ACCESS_2023_3323353 crossref_primary_10_1007_s00500_020_05419_0 crossref_primary_10_1007_s11042_021_11300_5 crossref_primary_10_1016_j_engappai_2021_104494 crossref_primary_10_1007_s11263_021_01453_z crossref_primary_10_1016_j_inffus_2025_103098 crossref_primary_10_1007_s11042_021_10965_2 crossref_primary_10_1007_s00607_022_01103_3 crossref_primary_10_3390_electronics14081538 crossref_primary_10_1007_s11042_021_11223_1 crossref_primary_10_1007_s11042_022_12564_1 crossref_primary_10_1109_ACCESS_2020_2990410 |
| Cites_doi | 10.1007/s11766-017-3466-8 10.1109/TBDATA.2016.2602849 10.1007/s11704-018-6442-4 10.1109/TASE.2014.2348555 10.1016/j.neucom.2017.10.040 10.1016/j.future.2017.11.046 10.1109/ACCESS.2016.2556680 10.1016/j.neucom.2017.12.063 10.1007/s11390-017-1764-5 10.1007/s11042-018-5697-y 10.1214/009053607000000677 10.1016/j.patcog.2017.02.013 10.1142/S0218843017410015 10.1016/j.knosys.2016.06.028 10.1007/s11042-018-6735-5 10.1016/j.neucom.2015.10.134 10.1016/j.knosys.2011.09.019 10.1016/j.aei.2016.10.005 10.1109/TII.2015.2443723 10.1016/j.knosys.2013.03.012 10.1016/j.neucom.2018.05.001 10.1109/TII.2014.2308433 10.1016/j.neucom.2017.07.051 10.1007/s11390-017-1714-2 10.1109/TSC.2015.2501981 10.1007/s11042-018-6690-1 10.1109/TNNLS.2015.2415257 10.3233/ICA-170544 10.1016/j.future.2017.09.073 |
| ContentType | Journal Article |
| Copyright | 2019 Elsevier B.V. |
| Copyright_xml | – notice: 2019 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.neucom.2018.12.025 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-8286 |
| EndPage | 148 |
| ExternalDocumentID | 10_1016_j_neucom_2018_12_025 S0925231218314796 |
| GroupedDBID | --- --K --M .DC .~1 0R~ 123 1B1 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXLA AAXUO AAYFN ABBOA ABCQJ ABFNM ABJNI ABMAC ABYKQ ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE AEBSH AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W KOM LG9 M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RIG ROL RPZ SDF SDG SDP SES SPC SPCBC SSN SSV SSZ T5K ZMT ~G- 29N 9DU AAQXK AATTM AAXKI AAYWO AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS FEDTE FGOYB HLZ HVGLF HZ~ R2- SBC SEW WUQ XPP ~HD |
| ID | FETCH-LOGICAL-c306t-8cdee8b44aa125b26a4b9d283c5a0f0b663761463f793f232f5bc3ea0ca5fa2a3 |
| ISICitedReferencesCount | 86 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000456410600014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0925-2312 |
| IngestDate | Sat Nov 29 03:02:59 EST 2025 Tue Nov 18 19:44:08 EST 2025 Fri Feb 23 02:27:02 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Neural network Knowledge distillation Recommender system Denoising Autoencoder |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c306t-8cdee8b44aa125b26a4b9d283c5a0f0b663761463f793f232f5bc3ea0ca5fa2a3 |
| ORCID | 0000-0001-9167-1683 0000-0002-8900-8054 |
| PageCount | 12 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_neucom_2018_12_025 crossref_primary_10_1016_j_neucom_2018_12_025 elsevier_sciencedirect_doi_10_1016_j_neucom_2018_12_025 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-03-07 |
| PublicationDateYYYYMMDD | 2019-03-07 |
| PublicationDate_xml | – month: 03 year: 2019 text: 2019-03-07 day: 07 |
| PublicationDecade | 2010 |
| PublicationTitle | Neurocomputing (Amsterdam) |
| PublicationYear | 2019 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Luo, Zhou, Li, You, Xia, Zhu (bib0013) 2016; 27 Luo, Zhou, Leung, Xia, Zhu, You, Li (bib0014) 2016; 13 G. Hinton, O. Vinyals, J. Dean, Distilling the Knowledge in a Neural Network, arXiv preprint. arXiv Sedhain, Menon, Sanner, Xie (bib0028) 2015 Li, Lv, Xie, Shang, Xia, Lu, Gu (bib0004) 2012; 28 Hu, Cao, Xu, Cao, Gu, Cao (bib0005) 2014 Zhang, Liu, Jin, Zhang (bib0007) 2018; 285 Rendle, Balby Marinho, Nanopoulos, Schmidt-Thieme (bib0044) 2009 K. Cho, B. van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, Y. Bengio, Learning phrase representations using rnn encoder-decoder for statistical machine translation, arXiv Xu, Yang, Gao, Lai, Yan (bib0039) 2018; 273 Wu, He, Zhang, Li (bib0002) 2018; 11 Vincent, Larochelle, Bengio, Manzagol (bib0041) 2008 Koren (bib0001) 2008 He, Zhang, Ren, Sun (bib0018) 2015 Bengio, Lamblin, Popovici, Larochelle, others (bib0040) 2006; 19 Luo, Zhou, Shang, Li, Xia (bib0015) 2016; 4 Bobadilla, Ortega, Hernando, Gutiérrez (bib0003) 2013; 46 Sarwar, Karypis, Konstan, Riedl (bib0010) 2001 Li, He, Yu (bib0024) 2018; 33 Yuan, Luo, Shang (bib0009) 2018; 275 Luo, Zhou, Xia, Zhu (bib0011) 2014; 10 Yang, Sun, Zhang, Zhang (bib0008) 2018; 308 Krizhevsky, Sutskever, Hinton (bib0017) 2012; 25 O. Kuchaiev, B. Ginsburg, Training deep autoencoders for collaborative filtering, arXiv (2015). Q. Li, X. Zheng, X. Wu, Collaborative Autoencoder for Recommender Systems: a unified framework for explicit and implicit feedback, arXiv preprint. arXiv Wu, DuBois, Zheng, Ester (bib0029) 2016 Zhang, He (bib0049) 2017; 24 [cs, stat]. (2017). (2017). Yan, He, Hou, Ai (bib0053) 2018; 27 Liu, Yang, Li, Zhou (bib0020) 2014 Zuo, Zeng, Gong, Jiao (bib0030) 2016; 204 Lv, He, Cai, Cheng (bib0050) 2017; 33 He, Liao, Zhang, Nie, Hu, Chua (bib0016) 2017 Tang, Wang, Zhang (bib0033) 2016 Chen, He, Yu (bib0027) 2018 Qi, Xu, Zhang, Dou, Hu, Zhou, Yu (bib0006) 2018; 4 [cs, stat], (2014). Yu, He, Pan (bib0025) 2018; 77 Mnih, Salakhutdinov (bib0035) 2008 He, Zhang, Ren, Sun (bib0036) 2016 Zlateski, Lee, Seung (bib0046) 2016 Yan, He, Chen (bib0052) 2017; 32 Wu, Wang, Liu (bib0043) 2016; 109 Luo, Zhou, Li, Xia, You, Zhu, Leung (bib0012) 2015; 11 Rendle, Freudenthaler (bib0045) 2014 Szegedy, Liu, Jia, Sermanet, Reed, Anguelov, Erhan, Vanhoucke, Rabinovich (bib0037) 2015 Li, He, Yu, Chen (bib0023) 2018 Lv, He, Cai, Cheng (bib0051) 2018; 28 Li, He, Yu, Chen (bib0022) 2017; 32 J. Dai, Y. Li, K. He, J. Sun, R-FCN: object detection via region-based fully convolutional networks, arXiv preprint. arXiv Zhou, He, Hou, Qiu (bib0047) 2018; 79 Hofmann, Schölkopf, Smola (bib0021) 2008; 36 (2016). Rendle, Freudenthaler, Gantner, Schmidt-Thieme (bib0042) 2009 Chen, He, Wu, Hou (bib0048) 2017; 67 Yu, He, Pan (bib0026) 2018 10.1016/j.neucom.2018.12.025_bib0034 Mnih (10.1016/j.neucom.2018.12.025_bib0035) 2008 Zlateski (10.1016/j.neucom.2018.12.025_bib0046) 2016 Yu (10.1016/j.neucom.2018.12.025_bib0025) 2018; 77 10.1016/j.neucom.2018.12.025_bib0038 Rendle (10.1016/j.neucom.2018.12.025_bib0045) 2014 Chen (10.1016/j.neucom.2018.12.025_bib0027) 2018 Sarwar (10.1016/j.neucom.2018.12.025_bib0010) 2001 Zhang (10.1016/j.neucom.2018.12.025_bib0049) 2017; 24 Koren (10.1016/j.neucom.2018.12.025_bib0001) 2008 Lv (10.1016/j.neucom.2018.12.025_bib0051) 2018; 28 Qi (10.1016/j.neucom.2018.12.025_bib0006) 2018; 4 Szegedy (10.1016/j.neucom.2018.12.025_bib0037) 2015 Zhang (10.1016/j.neucom.2018.12.025_bib0007) 2018; 285 Yuan (10.1016/j.neucom.2018.12.025_bib0009) 2018; 275 Wu (10.1016/j.neucom.2018.12.025_bib0002) 2018; 11 Hu (10.1016/j.neucom.2018.12.025_bib0005) 2014 Luo (10.1016/j.neucom.2018.12.025_bib0013) 2016; 27 Zuo (10.1016/j.neucom.2018.12.025_bib0030) 2016; 204 Yan (10.1016/j.neucom.2018.12.025_bib0052) 2017; 32 Li (10.1016/j.neucom.2018.12.025_bib0004) 2012; 28 Bobadilla (10.1016/j.neucom.2018.12.025_bib0003) 2013; 46 Yang (10.1016/j.neucom.2018.12.025_bib0008) 2018; 308 Luo (10.1016/j.neucom.2018.12.025_bib0014) 2016; 13 Rendle (10.1016/j.neucom.2018.12.025_bib0042) 2009 Wu (10.1016/j.neucom.2018.12.025_bib0029) 2016 Zhou (10.1016/j.neucom.2018.12.025_bib0047) 2018; 79 Luo (10.1016/j.neucom.2018.12.025_bib0011) 2014; 10 Krizhevsky (10.1016/j.neucom.2018.12.025_sbref0017) 2012; 25 Li (10.1016/j.neucom.2018.12.025_bib0023) 2018 Bengio (10.1016/j.neucom.2018.12.025_bib0040) 2006; 19 Li (10.1016/j.neucom.2018.12.025_bib0024) 2018; 33 Lv (10.1016/j.neucom.2018.12.025_bib0050) 2017; 33 He (10.1016/j.neucom.2018.12.025_bib0016) 2017 10.1016/j.neucom.2018.12.025_bib0019 Tang (10.1016/j.neucom.2018.12.025_bib0033) 2016 He (10.1016/j.neucom.2018.12.025_sbref0031) 2016 Yan (10.1016/j.neucom.2018.12.025_bib0053) 2018; 27 Vincent (10.1016/j.neucom.2018.12.025_bib0041) 2008 He (10.1016/j.neucom.2018.12.025_sbref0018) 2015 Li (10.1016/j.neucom.2018.12.025_bib0022) 2017; 32 Sedhain (10.1016/j.neucom.2018.12.025_bib0028) 2015 Yu (10.1016/j.neucom.2018.12.025_bib0026) 2018 Luo (10.1016/j.neucom.2018.12.025_bib0012) 2015; 11 Wu (10.1016/j.neucom.2018.12.025_bib0043) 2016; 109 Luo (10.1016/j.neucom.2018.12.025_bib0015) 2016; 4 Chen (10.1016/j.neucom.2018.12.025_bib0048) 2017; 67 Liu (10.1016/j.neucom.2018.12.025_bib0020) 2014 Xu (10.1016/j.neucom.2018.12.025_bib0039) 2018; 273 Rendle (10.1016/j.neucom.2018.12.025_bib0044) 2009 Hofmann (10.1016/j.neucom.2018.12.025_bib0021) 2008; 36 10.1016/j.neucom.2018.12.025_bib0032 10.1016/j.neucom.2018.12.025_bib0031 |
| References_xml | – year: 2018 ident: bib0027 article-title: A matting method based on full feature coverage publication-title: Multimedia Tools Appl. – start-page: 1861 year: 2014 end-page: 1867 ident: bib0005 article-title: Deep modeling of group preferences for group-based recommendation publication-title: Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence – reference: K. Cho, B. van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, Y. Bengio, Learning phrase representations using rnn encoder-decoder for statistical machine translation, arXiv: – start-page: 1 year: 2015 end-page: 9 ident: bib0037 article-title: Going deeper with convolutions publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 28 start-page: 41 year: 2018 end-page: 62 ident: bib0051 article-title: Supporting selective undo of string-wise operations for collaborative editing systems publication-title: Fut. Gen. Comput. Syst. – volume: 11 start-page: 946 year: 2015 end-page: 956 ident: bib0012 article-title: An efficient second-order approach to factorize sparse matrices in recommender systems publication-title: IEEE Trans. Ind. Inf. – start-page: 173 year: 2017 end-page: 182 ident: bib0016 article-title: Neural collaborative filtering publication-title: Proceedings of the Twenty-Sixth International Conference on World Wide Web – volume: 79 start-page: 473 year: 2018 end-page: 487 ident: bib0047 article-title: Parallel ant colony optimization on multi-core SIMD CPUs publication-title: Fut. Gen. Comput. Syst. – volume: 4 start-page: 301 year: 2018 end-page: 312 ident: bib0006 article-title: Structural balance theory-based E-commerce recommendation over big rating data publication-title: IEEE Trans. Big Data – volume: 32 start-page: 294 year: 2017 end-page: 312 ident: bib0022 article-title: A correlative classifiers approach based on particle filter and sample set for tracking occluded target publication-title: Appl. Math. A J. Chin. Univ. – reference: (2015). – start-page: 727 year: 2009 end-page: 736 ident: bib0044 article-title: Learning optimal ranking with tensor factorization for tag recommendation publication-title: Proceedings of the Fifteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – volume: 204 start-page: 51 year: 2016 end-page: 60 ident: bib0030 article-title: Tag-aware recommender systems based on deep neural networks publication-title: Neurocomputing – volume: 24 start-page: 261 year: 2017 end-page: 277 ident: bib0049 article-title: An efficient approach to directly compute the exact Hausdorff distance for 3D point sets publication-title: Integr. Comput. Aided Eng. – start-page: 1257 year: 2008 end-page: 1264 ident: bib0035 article-title: Probabilistic matrix factorization publication-title: Advances in Neural Information Processing Systems 20 – reference: , [cs, stat]. (2017). – volume: 285 start-page: 94 year: 2018 end-page: 103 ident: bib0007 article-title: A dynamic trust based two-layer neighbor selection scheme towards online recommender systems publication-title: Neurocomputing – volume: 273 start-page: 260 year: 2018 end-page: 270 ident: bib0039 article-title: SRNN: self-regularized neural network publication-title: Neurocomputing – volume: 13 start-page: 333 year: 2016 end-page: 343 ident: bib0014 article-title: An incremental-and-static-combined scheme for matrix-factorization-based collaborative filtering publication-title: IEEE Trans. Autom. Sci. Eng. – start-page: 1491 year: 2014 end-page: 1500 ident: bib0020 article-title: A recursive recurrent neural network for statistical machine translation publication-title: Proceedings of the ACL – volume: 19 start-page: 153 year: 2006 ident: bib0040 article-title: Greedy layer-wise training of deep networks publication-title: Adv. Neural Inf. Process. Syst. – start-page: 273 year: 2014 end-page: 282 ident: bib0045 article-title: Improving pairwise learning for item recommendation from implicit feedback publication-title: Proceedings of the Seventh ACM International Conference on Web Search and Data Mining – volume: 11 start-page: 341 year: 2018 end-page: 353 ident: bib0002 article-title: Service-oriented feature-based data exchange for cloud-based design and manufacturing publication-title: IEEE Trans. Serv. Comput. – volume: 67 start-page: 139 year: 2017 end-page: 148 ident: bib0048 article-title: A local start search algorithm to compute exact Hausdorff Distance for arbitrary point sets publication-title: Pattern Recognit. – volume: 308 start-page: 205 year: 2018 end-page: 226 ident: bib0008 article-title: Uncovering anomalous rating behaviors for rating systems publication-title: Neurocomputing – start-page: 111 year: 2015 end-page: 112 ident: bib0028 article-title: AutoRec: autoencoders meet collaborative filtering publication-title: Proceedings of the Twenty-Fourth International Conference on World Wide Web – start-page: 1096 year: 2008 end-page: 1103 ident: bib0041 article-title: Extracting and composing robust features with denoising autoencoders publication-title: Proceedings of the Twenty-Fifth International Conference on Machine Learning – volume: 36 start-page: 1171 year: 2008 end-page: 1220 ident: bib0021 article-title: Kernel methods in machine learning publication-title: Ann. Stat. – reference: , [cs, stat], (2014). – reference: (2017). – volume: 10 start-page: 1273 year: 2014 end-page: 1284 ident: bib0011 article-title: An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender systems publication-title: IEEE Trans. Ind. Inf. – volume: 27 start-page: 579 year: 2016 end-page: 592 ident: bib0013 article-title: A nonnegative latent factor model for large-scale sparse matrices in recommender systems via alternating direction method publication-title: IEEE Trans. Neural Netw. Learn. Syst. – start-page: 426 year: 2008 end-page: 434 ident: bib0001 article-title: Factorization meets the neighborhood: a multifaceted collaborative filtering model publication-title: Proceedings of the Fourteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – volume: 275 start-page: 2019 year: 2018 end-page: 2030 ident: bib0009 article-title: Effects of preprocessing and training biases in latent factor models for recommender systems publication-title: Neurocomputing – volume: 109 start-page: 90 year: 2016 end-page: 103 ident: bib0043 article-title: Recurrent neural network based recommendation for time heterogeneous feedback publication-title: Knowl. Based Syst. – reference: (2016). – start-page: 285 year: 2001 end-page: 295 ident: bib0010 article-title: Item-based collaborative filtering recommendation algorithms publication-title: Proceedings of the Tenth International Conference on World Wide Web – start-page: 770 year: 2016 end-page: 778 ident: bib0036 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 73:1 year: 2016 end-page: 73:12 ident: bib0046 article-title: ZNNi: maximizing the inference throughput of 3d convolutional networks on CPUs and GPUs publication-title: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis – volume: 46 start-page: 109 year: 2013 end-page: 132 ident: bib0003 article-title: Recommender systems survey publication-title: Knowl. Based Syst. – start-page: 5900 year: 2016 end-page: 5904 ident: bib0033 article-title: Recurrent neural network training with dark knowledge transfer publication-title: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) – start-page: 452 year: 2009 end-page: 461 ident: bib0042 article-title: BPR: Bayesian personalized ranking from implicit feedback publication-title: Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence – volume: 32 start-page: 340 year: 2017 end-page: 355 ident: bib0052 article-title: A novel hardware/software partitioning method based on position disturbed particle swarm optimization with invasive weed optimization publication-title: J. Comput. Sci. Technol. – volume: 4 start-page: 2649 year: 2016 end-page: 2655 ident: bib0015 article-title: A novel approach to extracting non-negative latent factors from non-negative big sparse matrices publication-title: IEEE Access – volume: 28 start-page: 1 year: 2012 end-page: 12 ident: bib0004 article-title: Interest-based real-time content recommendation in online social communities publication-title: Knowl. Based Syst. – reference: J. Dai, Y. Li, K. He, J. Sun, R-FCN: object detection via region-based fully convolutional networks, arXiv preprint. arXiv: – volume: 77 start-page: 24097 year: 2018 end-page: 24119 ident: bib0025 article-title: A novel region-based active contour model via local patch similarity measure for image segmentation publication-title: Multimedia Tools Appl. – volume: 33 start-page: 223 year: 2018 end-page: 236 ident: bib0024 article-title: Robust visual tracking based on convolutional features with illumination and occlusion handing publication-title: J. Comput. Sci. Technol. – year: 2018 ident: bib0026 article-title: A novel segmentation model for medical images with intensity inhomogeneity based on adaptive perturbation publication-title: Multimedia Tools Appl. – start-page: 153 year: 2016 end-page: 162 ident: bib0029 article-title: Collaborative denoising auto-encoders for top-N recommender systems publication-title: Proceedings of the Ninth ACM International Conference on Web Search and Data Mining – volume: 33 start-page: 397 year: 2017 end-page: 409 ident: bib0050 article-title: A string-wise CRDT algorithm for smart and large-scale collaborative editing systems publication-title: Adv. Eng. Inf. – volume: 25 start-page: 1097 year: 2012 end-page: 1105 ident: bib0017 article-title: ImageNet classification with deep convolutional neural networks publication-title: Advances in Neural Information Processing Systems – volume: 27 start-page: 1741001 year: 2018 ident: bib0053 article-title: An efficient particle swarm optimization for large-scale hardware/software co-design system publication-title: Int. J. Cooper. Inf. Syst. – reference: G. Hinton, O. Vinyals, J. Dean, Distilling the Knowledge in a Neural Network, arXiv preprint. arXiv: – reference: O. Kuchaiev, B. Ginsburg, Training deep autoencoders for collaborative filtering, arXiv: – year: 2018 ident: bib0023 article-title: A parallel and robust object tracking approach synthesizing adaptive Bayesian learning and improved incremental subspace learning publication-title: Front. Comput. Sci. – reference: Q. Li, X. Zheng, X. Wu, Collaborative Autoencoder for Recommender Systems: a unified framework for explicit and implicit feedback, arXiv preprint. arXiv: – start-page: 1026 year: 2015 end-page: 1034 ident: bib0018 article-title: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification publication-title: Proceedings of the IEEE International Conference on Computer Vision (ICCV) – volume: 32 start-page: 294 year: 2017 ident: 10.1016/j.neucom.2018.12.025_bib0022 article-title: A correlative classifiers approach based on particle filter and sample set for tracking occluded target publication-title: Appl. Math. A J. Chin. Univ. doi: 10.1007/s11766-017-3466-8 – volume: 4 start-page: 301 issue: 3 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0006 article-title: Structural balance theory-based E-commerce recommendation over big rating data publication-title: IEEE Trans. Big Data doi: 10.1109/TBDATA.2016.2602849 – year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0023 article-title: A parallel and robust object tracking approach synthesizing adaptive Bayesian learning and improved incremental subspace learning publication-title: Front. Comput. Sci. doi: 10.1007/s11704-018-6442-4 – volume: 13 start-page: 333 year: 2016 ident: 10.1016/j.neucom.2018.12.025_bib0014 article-title: An incremental-and-static-combined scheme for matrix-factorization-based collaborative filtering publication-title: IEEE Trans. Autom. Sci. Eng. doi: 10.1109/TASE.2014.2348555 – start-page: 1861 year: 2014 ident: 10.1016/j.neucom.2018.12.025_bib0005 article-title: Deep modeling of group preferences for group-based recommendation – ident: 10.1016/j.neucom.2018.12.025_bib0034 – ident: 10.1016/j.neucom.2018.12.025_bib0038 – volume: 275 start-page: 2019 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0009 article-title: Effects of preprocessing and training biases in latent factor models for recommender systems publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.10.040 – volume: 28 start-page: 41 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0051 article-title: Supporting selective undo of string-wise operations for collaborative editing systems publication-title: Fut. Gen. Comput. Syst. doi: 10.1016/j.future.2017.11.046 – start-page: 111 year: 2015 ident: 10.1016/j.neucom.2018.12.025_bib0028 article-title: AutoRec: autoencoders meet collaborative filtering – volume: 25 start-page: 1097 year: 2012 ident: 10.1016/j.neucom.2018.12.025_sbref0017 article-title: ImageNet classification with deep convolutional neural networks – volume: 4 start-page: 2649 year: 2016 ident: 10.1016/j.neucom.2018.12.025_bib0015 article-title: A novel approach to extracting non-negative latent factors from non-negative big sparse matrices publication-title: IEEE Access doi: 10.1109/ACCESS.2016.2556680 – volume: 285 start-page: 94 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0007 article-title: A dynamic trust based two-layer neighbor selection scheme towards online recommender systems publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.12.063 – volume: 33 start-page: 223 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0024 article-title: Robust visual tracking based on convolutional features with illumination and occlusion handing publication-title: J. Comput. Sci. Technol. doi: 10.1007/s11390-017-1764-5 – start-page: 770 year: 2016 ident: 10.1016/j.neucom.2018.12.025_sbref0031 article-title: Deep residual learning for image recognition – start-page: 1096 year: 2008 ident: 10.1016/j.neucom.2018.12.025_bib0041 article-title: Extracting and composing robust features with denoising autoencoders – start-page: 1026 year: 2015 ident: 10.1016/j.neucom.2018.12.025_sbref0018 article-title: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification – start-page: 727 year: 2009 ident: 10.1016/j.neucom.2018.12.025_bib0044 article-title: Learning optimal ranking with tensor factorization for tag recommendation – start-page: 1491 year: 2014 ident: 10.1016/j.neucom.2018.12.025_bib0020 article-title: A recursive recurrent neural network for statistical machine translation – volume: 77 start-page: 24097 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0025 article-title: A novel region-based active contour model via local patch similarity measure for image segmentation publication-title: Multimedia Tools Appl. doi: 10.1007/s11042-018-5697-y – volume: 36 start-page: 1171 year: 2008 ident: 10.1016/j.neucom.2018.12.025_bib0021 article-title: Kernel methods in machine learning publication-title: Ann. Stat. doi: 10.1214/009053607000000677 – volume: 67 start-page: 139 year: 2017 ident: 10.1016/j.neucom.2018.12.025_bib0048 article-title: A local start search algorithm to compute exact Hausdorff Distance for arbitrary point sets publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2017.02.013 – volume: 27 start-page: 1741001 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0053 article-title: An efficient particle swarm optimization for large-scale hardware/software co-design system publication-title: Int. J. Cooper. Inf. Syst. doi: 10.1142/S0218843017410015 – volume: 19 start-page: 153 year: 2006 ident: 10.1016/j.neucom.2018.12.025_bib0040 article-title: Greedy layer-wise training of deep networks publication-title: Adv. Neural Inf. Process. Syst. – volume: 109 start-page: 90 year: 2016 ident: 10.1016/j.neucom.2018.12.025_bib0043 article-title: Recurrent neural network based recommendation for time heterogeneous feedback publication-title: Knowl. Based Syst. doi: 10.1016/j.knosys.2016.06.028 – start-page: 452 year: 2009 ident: 10.1016/j.neucom.2018.12.025_bib0042 article-title: BPR: Bayesian personalized ranking from implicit feedback – start-page: 285 year: 2001 ident: 10.1016/j.neucom.2018.12.025_bib0010 article-title: Item-based collaborative filtering recommendation algorithms – year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0026 article-title: A novel segmentation model for medical images with intensity inhomogeneity based on adaptive perturbation publication-title: Multimedia Tools Appl. doi: 10.1007/s11042-018-6735-5 – start-page: 73:1 year: 2016 ident: 10.1016/j.neucom.2018.12.025_bib0046 article-title: ZNNi: maximizing the inference throughput of 3d convolutional networks on CPUs and GPUs – volume: 204 start-page: 51 year: 2016 ident: 10.1016/j.neucom.2018.12.025_bib0030 article-title: Tag-aware recommender systems based on deep neural networks publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.10.134 – start-page: 153 year: 2016 ident: 10.1016/j.neucom.2018.12.025_bib0029 article-title: Collaborative denoising auto-encoders for top-N recommender systems – volume: 28 start-page: 1 year: 2012 ident: 10.1016/j.neucom.2018.12.025_bib0004 article-title: Interest-based real-time content recommendation in online social communities publication-title: Knowl. Based Syst. doi: 10.1016/j.knosys.2011.09.019 – ident: 10.1016/j.neucom.2018.12.025_bib0032 – volume: 33 start-page: 397 year: 2017 ident: 10.1016/j.neucom.2018.12.025_bib0050 article-title: A string-wise CRDT algorithm for smart and large-scale collaborative editing systems publication-title: Adv. Eng. Inf. doi: 10.1016/j.aei.2016.10.005 – volume: 11 start-page: 946 year: 2015 ident: 10.1016/j.neucom.2018.12.025_bib0012 article-title: An efficient second-order approach to factorize sparse matrices in recommender systems publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2015.2443723 – start-page: 426 year: 2008 ident: 10.1016/j.neucom.2018.12.025_bib0001 article-title: Factorization meets the neighborhood: a multifaceted collaborative filtering model – volume: 46 start-page: 109 year: 2013 ident: 10.1016/j.neucom.2018.12.025_bib0003 article-title: Recommender systems survey publication-title: Knowl. Based Syst. doi: 10.1016/j.knosys.2013.03.012 – volume: 308 start-page: 205 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0008 article-title: Uncovering anomalous rating behaviors for rating systems publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.05.001 – volume: 10 start-page: 1273 year: 2014 ident: 10.1016/j.neucom.2018.12.025_bib0011 article-title: An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender systems publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2014.2308433 – start-page: 1257 year: 2008 ident: 10.1016/j.neucom.2018.12.025_bib0035 article-title: Probabilistic matrix factorization – ident: 10.1016/j.neucom.2018.12.025_bib0019 – start-page: 1 year: 2015 ident: 10.1016/j.neucom.2018.12.025_bib0037 article-title: Going deeper with convolutions – volume: 273 start-page: 260 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0039 article-title: SRNN: self-regularized neural network publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.07.051 – volume: 32 start-page: 340 year: 2017 ident: 10.1016/j.neucom.2018.12.025_bib0052 article-title: A novel hardware/software partitioning method based on position disturbed particle swarm optimization with invasive weed optimization publication-title: J. Comput. Sci. Technol. doi: 10.1007/s11390-017-1714-2 – start-page: 273 year: 2014 ident: 10.1016/j.neucom.2018.12.025_bib0045 article-title: Improving pairwise learning for item recommendation from implicit feedback – volume: 11 start-page: 341 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0002 article-title: Service-oriented feature-based data exchange for cloud-based design and manufacturing publication-title: IEEE Trans. Serv. Comput. doi: 10.1109/TSC.2015.2501981 – year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0027 article-title: A matting method based on full feature coverage publication-title: Multimedia Tools Appl. doi: 10.1007/s11042-018-6690-1 – volume: 27 start-page: 579 year: 2016 ident: 10.1016/j.neucom.2018.12.025_bib0013 article-title: A nonnegative latent factor model for large-scale sparse matrices in recommender systems via alternating direction method publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2015.2415257 – ident: 10.1016/j.neucom.2018.12.025_bib0031 – start-page: 5900 year: 2016 ident: 10.1016/j.neucom.2018.12.025_bib0033 article-title: Recurrent neural network training with dark knowledge transfer – volume: 24 start-page: 261 year: 2017 ident: 10.1016/j.neucom.2018.12.025_bib0049 article-title: An efficient approach to directly compute the exact Hausdorff distance for 3D point sets publication-title: Integr. Comput. Aided Eng. doi: 10.3233/ICA-170544 – volume: 79 start-page: 473 year: 2018 ident: 10.1016/j.neucom.2018.12.025_bib0047 article-title: Parallel ant colony optimization on multi-core SIMD CPUs publication-title: Fut. Gen. Comput. Syst. doi: 10.1016/j.future.2017.09.073 – start-page: 173 year: 2017 ident: 10.1016/j.neucom.2018.12.025_bib0016 article-title: Neural collaborative filtering |
| SSID | ssj0017129 |
| Score | 2.530776 |
| Snippet | In most recommender systems, the data of user feedbacks are usually represented with a set of discrete values, which are difficult to exactly describe users’... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 137 |
| SubjectTerms | Denoising Autoencoder Knowledge distillation Neural network Recommender system |
| Title | A novel Enhanced Collaborative Autoencoder with knowledge distillation for top-N recommender systems |
| URI | https://dx.doi.org/10.1016/j.neucom.2018.12.025 |
| Volume | 332 |
| WOSCitedRecordID | wos000456410600014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: ScienceDirect database customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Pa9swFBZZu8Mu-z3atRs67BY0YtmO5KMpGd0OobAOspORZWltSZzQOqEM9r_3PUl2vGXsF-xigolsoff56dMnvfcIeWNTrvTYjFgluIIFiixZZvCUeZTYUlmeyNgXmxDTqZzNsrPB4FsbC7OZi7qWt7fZ6r-aGu6BsTF09i_M3T0UbsBvMDpcwexw_SPD58N6uTHz4aS-8Lv7J1tTb8wwXzdLTF6JOSScCNuparhZ02ARou3xw-WKTYe4Zl4sXMm5kPj5pk9pXXoP7YpDBNkhX2D2hQqh1skMZ15o_QwMN8yVToB13Fl9vbjsvM_aTYYKS2p_6UsSGAUVM1-71utkO7EyXnDkKQM26X2v8e5WCu4C2fv-OA6Cp_eokc8JEybnyKfl3PH7XoK4elubNR4Cgk5Jp_L6oOofMmp_xK5gT8CdRYnIxvfIPhdpBk5xP38_mX3otqFExH2yxtD1NvbSHRDcfdfPuU2Pr5w_Jg_DQoPmHiBPyMDUT8mjtogHDT79Galy6vBCW7zQ7_BCe3ihiBfa4YX28UIBL9ThhfbwQgNenpNP7ybnJ6cslN5gGtaQDZO6MkaWSaIUMOCSj1VSZhVQUZ2qkR2VwFMFfM7j2IJ_t8DKbVrq2KiRVqlVXMUvyF69rM0BoWlSWRVpzitkj8pmlU6BZ0uTSB7bLDokcTtohQ556bE8yrxoDyBeFX6oCxzqIuIFDPUhYV2rlc_L8pv_i9YeReCWnjMWAKFftnz5zy2PyIPt13FM9prrtXlF7utNc3lz_Tpg7Q6cpKKj |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+novel+Enhanced+Collaborative+Autoencoder+with+knowledge+distillation+for+top-N+recommender+systems&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Pan%2C+Yiteng&rft.au=He%2C+Fazhi&rft.au=Yu%2C+Haiping&rft.date=2019-03-07&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.eissn=1872-8286&rft.volume=332&rft.spage=137&rft.epage=148&rft_id=info:doi/10.1016%2Fj.neucom.2018.12.025&rft.externalDocID=S0925231218314796 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon |